Function htmlParseDocument

ThirdParty/libxml2/vtklibxml2/HTMLparser.c:4749–4851

 */

int
htmlParseDocument(htmlParserCtxtPtr ctxt) {
    xmlDtdPtr dtd;

    if ((ctxt == NULL) || (ctxt->input == NULL))
	return(-1);

    if ((ctxt->sax) && (ctxt->sax->setDocumentLocator)) {
        ctxt->sax->setDocumentLocator(ctxt->userData,
                (xmlSAXLocator *) &xmlDefaultSAXLocator);
    }

    xmlDetectEncoding(ctxt);

    /*
     * This is wrong but matches long-standing behavior. In most cases,
     * a document starting with an XML declaration will specify UTF-8.
     */
    if (((ctxt->input->flags & XML_INPUT_HAS_ENCODING) == 0) &&
        (xmlStrncmp(ctxt->input->cur, BAD_CAST "<?xm", 4) == 0))
        xmlSwitchEncoding(ctxt, XML_CHAR_ENCODING_UTF8);

    /*
     * Wipe out everything which is before the first '<'
     */
    SKIP_BLANKS;
    if (CUR == 0) {
	htmlParseErr(ctxt, XML_ERR_DOCUMENT_EMPTY,
	             "Document is empty\n", NULL, NULL);
    }

    if ((ctxt->sax) && (ctxt->sax->startDocument) && (!ctxt->disableSAX))
	ctxt->sax->startDocument(ctxt->userData);

    /*
     * Parse possible comments and PIs before any content
     */
    while (((CUR == '<') && (NXT(1) == '!') &&
            (NXT(2) == '-') && (NXT(3) == '-')) ||
	   ((CUR == '<') && (NXT(1) == '?'))) {
        htmlParseComment(ctxt);
        htmlParsePI(ctxt);
	SKIP_BLANKS;
    }


    /*
     * Then possibly doc type declaration(s) and more Misc
     * (doctypedecl Misc*)?
     */
    if ((CUR == '<') && (NXT(1) == '!') &&
	(UPP(2) == 'D') && (UPP(3) == 'O') &&
	(UPP(4) == 'C') && (UPP(5) == 'T') &&
	(UPP(6) == 'Y') && (UPP(7) == 'P') &&
	(UPP(8) == 'E')) {
	htmlParseDocTypeDecl(ctxt);
    }
    SKIP_BLANKS;